Financial crime investigators face many challenges when analyzing disconnected data to build cases to combat transnational crime. The inundation of information makes efficient analysis difficult when working to recognize patterns and prioritize leads to develop investigations. This presentation explores the challenges faced by law enforcement, AML professionals, financial intelligence units, and other investigators combating illicit finance through the use of Suspicious Activity Reports (SARs) and other regulatory reports. We propose a data-driven approach to solving these challenges which leverages entity resolution, Natural Language Processing (NLP), network generation and network analytics. This approach enhances crime fighting capabilities by using risk-prioritization to efficiently triage the totality of information available, leading to a higher level of financial intelligence, more effective disruption of criminal networks, and increased recovery of assets.
Presenting Company: SAS
Watch the recording
